A screening methodology based on Random Forests to improve the detection of gene-gene interactions.

Publisher: Nature Publishing Group Country of Publication: England NLM ID: 9302235 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1476-5438 (Electronic) Linking ISSN: 10184813 NLM ISO Abbreviation: Eur J Hum Genet Subsets: MEDLINE

Publication: <2003->: London : Nature Publishing Group
Original Publication: Basel ; New York : Karger, [1992-

Decision Trees* ; Epistasis, Genetic* ; Genetic Association Studies* ; Models, Genetic*; Computational Biology/*methods; Algorithms ; Asthma/genetics ; Computer Simulation ; Europe ; Gene Expression ; Genetic Markers ; Genetic Predisposition to Disease ; Genetic Testing ; Humans ; Multifactor Dimensionality Reduction ; Polymorphism, Single Nucleotide ; Statistics as Topic

The search for susceptibility loci in gene-gene interactions imposes a methodological and computational challenge for statisticians because of the large dimensionality inherent to the modelling of gene-gene interactions or epistasis. In an era in which genome-wide scans have become relatively common, new powerful methods are required to handle the huge amount of feasible gene-gene interactions and to weed out false positives and negatives from these results. One solution to the dimensionality problem is to reduce data by preliminary screening of markers to select the best candidates for further analysis. Ideally, this screening step is statistically independent of the testing phase. Initially developed for small numbers of markers, the Multifactor Dimensionality Reduction (MDR) method is a nonparametric, model-free data reduction technique to associate sets of markers with optimal predictive properties to disease. In this study, we examine the power of MDR in larger data sets and compare it with other approaches that are able to identify gene-gene interactions. Under various interaction models (purely and not purely epistatic), we use a Random Forest (RF)-based prescreening method, before executing MDR, to improve its performance. We find that the power of MDR increases when noisy SNPs are first removed, by creating a collection of candidate markers with RFs. We validate our technique by extensive simulation studies and by application to asthma data from the European Committee of Respiratory Health Study II.

Hum Mol Genet. 2006 May 15;15(10):1667-79. (PMID: 16600990)
Nat Genet. 2003 Nov;35(3):258-63. (PMID: 14566338)
Genet Epidemiol. 2009 Jan;33(1):87-94. (PMID: 18671250)
Hum Hered. 2009;67(3):183-92. (PMID: 19077437)
J Med Genet. 2009 Mar;46(3):159-67. (PMID: 18285428)
Am J Hum Genet. 2006 Jan;78(1):15-27. (PMID: 16385446)
Nat Rev Genet. 2004 May;5(5):376-87. (PMID: 15143320)
Biometrics. 2000 Mar;56(1):52-8. (PMID: 10783776)
Am J Hum Genet. 2001 Jul;69(1):138-47. (PMID: 11404819)
Am J Physiol Lung Cell Mol Physiol. 2006 Nov;291(5):L1005-17. (PMID: 16829631)
Nat Genet. 2005 Apr;37(4):413-7. (PMID: 15793588)
Eur Respir J. 2008 Aug;32(2):350-61. (PMID: 18385169)
Science. 2004 Apr 9;304(5668):300-4. (PMID: 15073379)
Genet Epidemiol. 2003 Feb;24(2):150-7. (PMID: 12548676)
Hum Hered. 2003;56(1-3):73-82. (PMID: 14614241)
Genet Epidemiol. 2005 Feb;28(2):171-82. (PMID: 15593090)
Biochem J. 2003 Jul 1;373(Pt 1):179-89. (PMID: 12662155)

0 (Genetic Markers)

Date Created: 20100513 Date Completed: 20110207 Latest Revision: 20211020

20231215

PMC2987456

10.1038/ejhg.2010.48

20461113